RDMA/core: Trace points for diagnosing completion queue issues

Sample trace events:

   kworker/u29:0-300   [007]   120.042217: cq_alloc:             cq.id=4 nr_cqe=161 comp_vector=2 poll_ctx=WORKQUEUE
          <idle>-0     [002]   120.056292: cq_schedule:          cq.id=4
    kworker/2:1H-482   [002]   120.056402: cq_process:           cq.id=4 wake-up took 109 [us] from interrupt
    kworker/2:1H-482   [002]   120.056407: cq_poll:              cq.id=4 requested 16, returned 1
          <idle>-0     [002]   120.067503: cq_schedule:          cq.id=4
    kworker/2:1H-482   [002]   120.067537: cq_process:           cq.id=4 wake-up took 34 [us] from interrupt
    kworker/2:1H-482   [002]   120.067541: cq_poll:              cq.id=4 requested 16, returned 1
          <idle>-0     [002]   120.067657: cq_schedule:          cq.id=4
    kworker/2:1H-482   [002]   120.067672: cq_process:           cq.id=4 wake-up took 15 [us] from interrupt
    kworker/2:1H-482   [002]   120.067674: cq_poll:              cq.id=4 requested 16, returned 1

 ...

         systemd-1     [002]   122.392653: cq_schedule:          cq.id=4
    kworker/2:1H-482   [002]   122.392688: cq_process:           cq.id=4 wake-up took 35 [us] from interrupt
    kworker/2:1H-482   [002]   122.392693: cq_poll:              cq.id=4 requested 16, returned 16
    kworker/2:1H-482   [002]   122.392836: cq_poll:              cq.id=4 requested 16, returned 16
    kworker/2:1H-482   [002]   122.392970: cq_poll:              cq.id=4 requested 16, returned 16
    kworker/2:1H-482   [002]   122.393083: cq_poll:              cq.id=4 requested 16, returned 16
    kworker/2:1H-482   [002]   122.393195: cq_poll:              cq.id=4 requested 16, returned 3

Several features to note in this output:
 - The WCE count and context type are reported at allocation time
 - The CPU and kworker for each CQ is evident
 - The CQ's restracker ID is tagged on each trace event
 - CQ poll scheduling latency is measured
 - Details about how often single completions occur versus multiple
   completions are evident
 - The cost of the ULP's completion handler is recorded

Link: https://lore.kernel.org/r/20191218201815.30584.3481.stgit@manet.1015granger.net
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

4 files changed, 44 insertions, 4 deletions

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index f22555f982e2..2b86a514c9bf 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -11,7 +11,8 @@ ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o \
 				roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \
 				multicast.o mad.o smi.o agent.o mad_rmpp.o \
-				nldev.o restrack.o counters.o ib_core_uverbs.o
+				nldev.o restrack.o counters.o ib_core_uverbs.o \
+				trace.o
 
 ib_core-$(CONFIG_SECURITY_INFINIBAND) += security.o
 ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index bbfded6d5d3d..4f25b2400694 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -7,6 +7,8 @@
 #include <linux/slab.h>
 #include <rdma/ib_verbs.h>
 
+#include <trace/events/rdma_core.h>
+
 /* # of WCs to poll for with a single call to ib_poll_cq */
 #define IB_POLL_BATCH			16
 #define IB_POLL_BATCH_DIRECT		8
@@ -41,6 +43,7 @@ static void ib_cq_rdma_dim_work(struct work_struct *w)
 
 	dim->state = DIM_START_MEASURE;
 
+	trace_cq_modify(cq, comps, usec);
 	cq->device->ops.modify_cq(cq, comps, usec);
 }
 
@@ -65,18 +68,29 @@ static void rdma_dim_init(struct ib_cq *cq)
 	INIT_WORK(&dim->work, ib_cq_rdma_dim_work);
 }
 
+static int __poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc)
+{
+	int rc;
+
+	rc = ib_poll_cq(cq, num_entries, wc);
+	trace_cq_poll(cq, num_entries, rc);
+	return rc;
+}
+
 static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *wcs,
 			   int batch)
 {
 	int i, n, completed = 0;
 
+	trace_cq_process(cq);
+
 	/*
 	 * budget might be (-1) if the caller does not
 	 * want to bound this call, thus we need unsigned
 	 * minimum here.
 	 */
-	while ((n = ib_poll_cq(cq, min_t(u32, batch,
-					 budget - completed), wcs)) > 0) {
+	while ((n = __poll_cq(cq, min_t(u32, batch,
+					budget - completed), wcs)) > 0) {
 		for (i = 0; i < n; i++) {
 			struct ib_wc *wc = &wcs[i];
 
@@ -131,8 +145,10 @@ static int ib_poll_handler(struct irq_poll *iop, int budget)
 	completed = __ib_process_cq(cq, budget, cq->wc, IB_POLL_BATCH);
 	if (completed < budget) {
 		irq_poll_complete(&cq->iop);
-		if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
+		if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) {
+			trace_cq_reschedule(cq);
 			irq_poll_sched(&cq->iop);
+		}
 	}
 
 	if (dim)
@@ -143,6 +159,7 @@ static int ib_poll_handler(struct irq_poll *iop, int budget)
 
 static void ib_cq_completion_softirq(struct ib_cq *cq, void *private)
 {
+	trace_cq_schedule(cq);
 	irq_poll_sched(&cq->iop);
 }
 
@@ -162,6 +179,7 @@ static void ib_cq_poll_work(struct work_struct *work)
 
 static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private)
 {
+	trace_cq_schedule(cq);
 	queue_work(cq->comp_wq, &cq->work);
 }
 
@@ -239,6 +257,7 @@ struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private,
 		goto out_destroy_cq;
 	}
 
+	trace_cq_alloc(cq, nr_cqe, comp_vector, poll_ctx);
 	return cq;
 
 out_destroy_cq:
@@ -248,6 +267,7 @@ out_free_wc:
 	kfree(cq->wc);
 out_free_cq:
 	kfree(cq);
+	trace_cq_alloc_error(nr_cqe, comp_vector, poll_ctx, ret);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL(__ib_alloc_cq_user);
@@ -304,6 +324,7 @@ void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata)
 		WARN_ON_ONCE(1);
 	}
 
+	trace_cq_free(cq);
 	rdma_restrack_del(&cq->res);
 	cq->device->ops.destroy_cq(cq, udata);
 	if (cq->dim)
diff --git a/drivers/infiniband/core/trace.c b/drivers/infiniband/core/trace.c
new file mode 100644
index 000000000000..6c3514beac4d
--- /dev/null
+++ b/drivers/infiniband/core/trace.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Trace points for core RDMA functions.
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved.
+ */
+
+#define CREATE_TRACE_POINTS
+
+#include <rdma/ib_verbs.h>
+
+#include <trace/events/rdma_core.h>
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index dd765e176cdd..289b2f7a9d5e 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -53,6 +53,8 @@
 
 #include "core_priv.h"
 
+#include <trace/events/rdma_core.h>
+
 static int ib_resolve_eth_dmac(struct ib_device *device,
 			       struct rdma_ah_attr *ah_attr);
 
@@ -2744,6 +2746,7 @@ void ib_drain_sq(struct ib_qp *qp)
 		qp->device->ops.drain_sq(qp);
 	else
 		__ib_drain_sq(qp);
+	trace_cq_drain_complete(qp->send_cq);
 }
 EXPORT_SYMBOL(ib_drain_sq);
 
@@ -2772,6 +2775,7 @@ void ib_drain_rq(struct ib_qp *qp)
 		qp->device->ops.drain_rq(qp);
 	else
 		__ib_drain_rq(qp);
+	trace_cq_drain_complete(qp->recv_cq);
 }
 EXPORT_SYMBOL(ib_drain_rq);